| Neural headline generation on abstract meaning representation S Takase, J Suzuki, N Okazaki, T Hirao, M Nagata Proceedings of the 2016 conference on empirical methods in natural language …, 2016 | 197 | 2016 |
| Positional encoding to control output sequence length S Takase, N Okazaki arXiv preprint arXiv:1904.07418, 2019 | 117 | 2019 |
| Lessons on parameter sharing across layers in transformers S Takase, S Kiyono arXiv preprint arXiv:2104.06022, 2021 | 73 | 2021 |
| Improving truthfulness of headline generation K Matsumaru, S Takase, N Okazaki arXiv preprint arXiv:2005.00882, 2020 | 49 | 2020 |
| Direct output connection for a high-rank language model S Takase, J Suzuki, M Nagata arXiv preprint arXiv:1808.10143, 2018 | 45 | 2018 |
| Rethinking perturbations in encoder-decoders for fast training S Takase, S Kiyono arXiv preprint arXiv:2104.01853, 2021 | 43 | 2021 |
| Handling multiword expressions in causality estimation S Sasaki, S Takase, N Inoue, N Okazaki, K Inui Proceedings of the 12th International Conference on Computational Semantics …, 2017 | 33 | 2017 |
| Character n-gram embeddings to improve RNN language models S Takase, J Suzuki, M Nagata Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 5074-5082, 2019 | 32 | 2019 |
| Multi-task learning for cross-lingual abstractive summarization S Takase, N Okazaki arXiv preprint arXiv:2010.07503, 2020 | 29 | 2020 |
| Interpretability for language learners using example-based grammatical error correction M Kaneko, S Takase, A Niwa, N Okazaki arXiv preprint arXiv:2203.07085, 2022 | 28 | 2022 |
| Exploring effectiveness of GPT-3 in grammatical error correction: A study on performance and controllability in prompt-based methods M Loem, M Kaneko, S Takase, N Okazaki arXiv preprint arXiv:2305.18156, 2023 | 27 | 2023 |
| An empirical study of building a strong baseline for constituency parsing J Suzuki, S Takase, H Kamigaito, M Morishita, M Nagata Proceedings of the 56th Annual Meeting of the Association for Computational …, 2018 | 23 | 2018 |
| Fast and large-scale unsupervised relation extraction S Takase, N Okazaki, K Inui Proceedings of the 29th Pacific Asia Conference on Language, Information and …, 2015 | 22 | 2015 |
| All word embeddings from one embedding S Takase, S Kobayashi Advances in Neural Information Processing Systems 33, 3775-3785, 2020 | 21 | 2020 |
| Joint optimization of tokenization and downstream model T Hiraoka, S Takase, K Uchiumi, A Keyaki, N Okazaki arXiv preprint arXiv:2105.12410, 2021 | 17 | 2021 |
| Optimizing word segmentation for downstream task T Hiraoka, S Takase, K Uchiumi, A Keyaki, N Okazaki Findings of the Association for Computational Linguistics: EMNLP 2020, 1341-1351, 2020 | 16 | 2020 |
| Modeling semantic compositionality of relational patterns S Takase, N Okazaki, K Inui Engineering Applications of Artificial Intelligence 50, 256-264, 2016 | 16 | 2016 |
| On layer normalizations and residual connections in transformers S Takase, S Kiyono, S Kobayashi, J Suzuki arXiv preprint arXiv:2206.00330, 2022 | 15 | 2022 |
| Source-side prediction for neural headline generation S Kiyono, S Takase, J Suzuki, N Okazaki, K Inui, M Nagata arXiv preprint arXiv:1712.08302, 2017 | 12 | 2017 |
| Composing distributed representations of relational patterns S Takase, N Okazaki, K Inui ACL, 2276-2286, 2016 | 12 | 2016 |
Jun SuzukiTohoku University確認したメール アドレス: tohoku.ac.jp
